Podcast Episodes

Back to Search
“AI catastrophes and rogue deployments” by Buck

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.[Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek…

2 years, 2 months ago

Short Long
View Episode
“Loving a world you don’t trust” by Joe Carlsmith

(Cross-posted from my website. Audio version here, or search for "Joe Carlsmith Audio" on your podcast app.)

This is the final essay in a series that …

2 years, 2 months ago

Short Long
View Episode
“LLM Generality is a Timeline Crux” by eggsyntax

Summary Summary .

LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.

Longer summary

Ther…

2 years, 2 months ago

Short Long
View Episode
“LLM Generality is a Timeline Crux” by eggsyntax

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short Summary

LLMs may be fundamentally incapable of fully gene…

2 years, 3 months ago

Short Long
View Episode
“LLM Generality is a Timeline Crux” by eggsyntax

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short Summary

LLMs may be fundamentally incapable of fully gene…

2 years, 3 months ago

Short Long
View Episode
“Formal verification, heuristic explanations and surprise accounting” by paulfchristiano

ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understand…

2 years, 3 months ago

Short Long
View Episode
“LLM Generality is a Timeline Crux” by eggsyntax

Summary Summary .

LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.

Longer summary

Ther…

2 years, 3 months ago

Short Long
View Episode
“SAE feature geometry is outside the superposition hypothesis” by jake_mendel

Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain cr…

2 years, 3 months ago

Short Long
View Episode
“Connecting the Dots: LLMs can Infer & Verbalize Latent Structure from Training Data” by Johannes Treutlein, Owain_Evans

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.TL;DR: We published a new paper on out-of-c…

2 years, 3 months ago

Short Long
View Episode
“Boycott OpenAI” by PeterMcCluskey

This is a link post.I have canceled my OpenAI subscription in protest over OpenAI's lack ofethics.

In particular, I object to:

threats to confiscate d…

2 years, 3 months ago

Short Long
View Episode

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us